Read in Data

# Get the Data

food_consumption <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-02-18/food_consumption.csv')
## Rows: 1430 Columns: 4
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): country, food_category
## dbl (2): consumption, co2_emmission
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
# Or read in with tidytuesdayR package (https://github.com/thebioengineer/tidytuesdayR)
# PLEASE NOTE TO USE 2020 DATA YOU NEED TO USE tidytuesdayR version ? from GitHub

# Either ISO-8601 date or year/week works!

# Install via devtools::install_github("thebioengineer/tidytuesdayR")

tuesdata <- tidytuesdayR::tt_load('2020-02-18')
## Only 10 Github queries remaining until 2022-02-15 11:41:25 PM EST.
## Only 10 Github queries remaining until 2022-02-15 11:41:25 PM EST.
## Only 10 Github queries remaining until 2022-02-15 11:41:25 PM EST.
## Only 10 Github queries remaining until 2022-02-15 11:41:25 PM EST.
## Only 10 Github queries remaining until 2022-02-15 11:41:25 PM EST.
## --- Compiling #TidyTuesday Information for 2020-02-18 ----
## Only 9 Github queries remaining until 2022-02-15 11:41:25 PM EST.
## --- There is 1 file available ---
## Only 8 Github queries remaining until 2022-02-15 11:41:25 PM EST.
## --- Starting Download ---
## Only 8 Github queries remaining until 2022-02-15 11:41:25 PM EST.
##  Downloading file 1 of 1: `food_consumption.csv`
## Only 7 Github queries remaining until 2022-02-15 11:41:24 PM EST.
## --- Download complete ---
tuesdata <- tidytuesdayR::tt_load(2020, week = 8)
## Only 6 Github queries remaining until 2022-02-15 11:41:24 PM EST.
## Only 6 Github queries remaining until 2022-02-15 11:41:24 PM EST.
## --- Compiling #TidyTuesday Information for 2020-02-18 ----
## Only 6 Github queries remaining until 2022-02-15 11:41:24 PM EST.
## --- There is 1 file available ---
## Only 5 Github queries remaining until 2022-02-15 11:41:24 PM EST.
## --- Starting Download ---
## Only 5 Github queries remaining until 2022-02-15 11:41:24 PM EST.
##  Downloading file 1 of 1: `food_consumption.csv`
## Only 4 Github queries remaining until 2022-02-15 11:41:25 PM EST.
## --- Download complete ---
food_consumption <- tuesdata$food_consumption

food_consumption
## # A tibble: 1,430 × 4
##    country   food_category            consumption co2_emmission
##    <chr>     <chr>                          <dbl>         <dbl>
##  1 Argentina Pork                           10.5          37.2 
##  2 Argentina Poultry                        38.7          41.5 
##  3 Argentina Beef                           55.5        1712   
##  4 Argentina Lamb & Goat                     1.56         54.6 
##  5 Argentina Fish                            4.36          6.96
##  6 Argentina Eggs                           11.4          10.5 
##  7 Argentina Milk - inc. cheese            195.          278.  
##  8 Argentina Wheat and Wheat Products      103.           19.7 
##  9 Argentina Rice                            8.77         11.2 
## 10 Argentina Soybeans                        0             0   
## # … with 1,420 more rows

Data Wrangling

food_consumption_total <- food_consumption %>%
  group_by(food_category) %>%
  summarize(total_consumption = sum(consumption),
            total_emission = sum(co2_emmission)) %>%
  mutate(food_type = case_when(food_category == "Pork" ~ "Animal Product",
                               food_category == "Poultry" ~ "Animal Product",
                               food_category == "Beef" ~ "Animal Product",
                               food_category == "Fish" ~ "Animal Product",
                               food_category == "Eggs" ~ "Animal Product",
                               food_category == "Milk - inc. cheese" ~ "Animal Product",
                               TRUE ~ "Non-Animal Product"))

food_consumption_total
## # A tibble: 11 × 4
##    food_category            total_consumption total_emission food_type         
##    <chr>                                <dbl>          <dbl> <chr>             
##  1 Beef                                 1576.        48633.  Animal Product    
##  2 Eggs                                 1061.          975.  Animal Product    
##  3 Fish                                 2247.         3588.  Animal Product    
##  4 Lamb & Goat                           338.        11837.  Non-Animal Product
##  5 Milk - inc. cheese                  16351.        23290   Animal Product    
##  6 Nuts inc. Peanut Butter               538.          952.  Non-Animal Product
##  7 Pork                                 2096.         7419.  Animal Product    
##  8 Poultry                              2758.         2963.  Animal Product    
##  9 Rice                                 3819.         4887.  Non-Animal Product
## 10 Soybeans                              112.           50.4 Non-Animal Product
## 11 Wheat and Wheat Products             9301.         1774.  Non-Animal Product

Visualization

plot_ly(data = food_consumption_total,
        type = "treemap",
        labels = ~ food_category,
        values = ~ total_consumption)